JP2023179669A - Cognitive analysis and disambiguation of electronic medical records for presentation of pertinent information for medical treatment plan - Google Patents

Abstract

To provide a method, apparatus, program and storage for performing cognitive analysis and disambiguation of electronic medical records for presentation of pertinent information for a medical treatment plan.SOLUTION: In a healthcare cognitive system, a cognitive analysis and disambiguation engine is configured to: receive a medical condition for a current or upcoming interaction with a patient; receive a medical mental model that emulates the thinking of a medical professional with regard to reviewing a patient electronic medical record (EMR) in order to identify pertinent information for a medical treatment plan to treat the medical condition; use the medical mental model to analyze the EMR for the patient in order to identify at least one portion of the EMR relevant to the medical treatment plan; analyze the identified at least one portion of the EMR in order to extract relevant patient information that is directed to the medical treatment plan for the medical condition; and use the medical mental model to generate and output a cognitive summary correlating the extracted relevant patient information and the medical treatment plan in association with the medical condition.SELECTED DRAWING: Figure 3

Description

TECHNICAL FIELD This application relates generally to improved data processing apparatus and methods, and more particularly to cognitive analysis and disambiguation mechanisms of electronic medical records for the presentation of relevant information regarding medical care plans.

An electronic health record (EHR) or electronic medical record (EMR) is an organized collection of patient and patient population health information stored electronically in digital format. These records can be shared across various healthcare settings. Records are shared through networked enterprise-wide information systems or other information networks and exchanges. The EMR can contain a range of data including demographics, medical history, medications and allergies, immune status, laboratory test results, radiology images, vital signs, personal demographic information such as age and weight, and payment information. can.

EMR systems are designed to accurately store data and capture patient conditions over time. This eliminates the need to comb through a patient's previous paper medical records and helps ensure that the data is accurate and readable. This reduces the risk of data being duplicated as there is only one file that can be changed, which increases the likelihood that the file is up-to-date and reduces the risk of losing paperwork. Because digital information is searchable and in a single file, EMR is more effective when extracting medical data for consideration of possible trends and long-term changes in patients. Studying medical records based on patient populations may be further facilitated by the widespread use of EMR.

This Summary is provided to introduce a selection of concepts in a simplified form that are further described herein in the Detailed Description. This Summary is not intended to identify key factors or essential features of the claimed subject matter, nor is it intended to be used in limiting the scope of the claimed subject matter.

In one illustrative embodiment, a method is provided in a data processing system comprising a processor and a memory, the memory performing recognition for analysis and disambiguation of electronic medical records for presentation of relevant information regarding a medical plan. Includes instructions executed by the processor to specifically configure the processor to implement the analysis engine. The method includes receiving medical conditions for a current or upcoming interaction with a patient by a cognitive analysis engine executing on a data processing system. The method uses a medical mental model that emulates a medical professional's thinking about reviewing a patient's electronic medical record (EMR) with a cognitive analytics engine to identify relevant information regarding the medical plan and treat the medical condition. further including receiving. The method further includes analyzing the patient's EMR with a cognitive analysis engine using the medical mental model to identify at least one portion of the EMR related to the medical care plan. The method further includes analyzing at least one portion of the identified EMR with a cognitive analysis engine using the medical mental model to extract relevant patient information for a medical plan regarding the medical condition. The method further includes using the medical mental model to generate and output, by the cognitive analysis engine, a cognitive summary that correlates with the extracted relevant patient information and medical care plan regarding the medical condition.

In other illustrative embodiments, a computer usable medium or a computer program product comprising a readable medium having a computer readable program is provided. The computer readable program, when executed on a computing device, causes the computing device to perform various of the operations outlined above for example embodiments of the method, and combinations thereof.

In yet another illustrative embodiment, a system/apparatus is provided. A system/apparatus may include one or more processors and memory coupled to the one or more processors. The memory includes instructions that, when executed by the one or more processors, cause the one or more processors to perform various of the operations outlined above for example embodiments of the method, and combinations thereof. be able to.

These and other features and advantages of the invention will be explained in the following detailed description of illustrative embodiments of the invention, or will become apparent to those skilled in the art upon viewing the detailed description. Dew.

The present invention, as well as preferred modes of use, and further objects and advantages thereof, may best be understood by reference to the following detailed description of illustrative embodiments, when read in conjunction with the accompanying drawings. Dew.

1 is a schematic diagram of one illustrative embodiment of a cognitive healthcare system in a computer network; FIG. FIG. 1 is a block diagram of an example data processing system in which aspects of the example embodiments are implemented. FIG. 2 is an illustrative diagram illustrating the interaction of elements of a healthcare cognitive system in accordance with one illustrative embodiment. FIG. 3 depicts an example medical mental model in accordance with an illustrative embodiment. FIG. 2 is a block diagram illustrating a mental model instantiation engine according to an illustrative embodiment. FIG. 2 is a block diagram illustrating a cognitive analysis and disambiguation engine according to an illustrative embodiment. 2 is a flowchart of a mechanism for instantiating a medical mental model according to an illustrative embodiment. 2 is a flow diagram illustrating the operation of a mechanism for cognitive analysis and disambiguation of electronic medical records for presentation of relevant information regarding a medical plan according to an illustrative embodiment.

Due to government regulations and advances in computing technology, many professionals and organizations store patient information in electronic medical records. As these electronic medical records (EMRs) grow in size, healthcare professionals are able to locate information within the EMR and eliminate ambiguities in order to identify the parts that are particularly relevant to the patient's medical condition being investigated by healthcare professionals. becomes more difficult to resolve. For example, if a health care professional is treating a patient in the hospital, the health care professional may want to identify specific areas that are relevant to a particular medical problem that the patient is complaining about, or that may be applied to the patient. It may be necessary to review the patient's medical history, as stored in the EMR, to identify areas of particular importance to previous treatment plans, or both. This can be a very difficult task, especially when integrating a large amount of EMR from a variety of disparate information sources, which prior to the implementation of EMR was a manual task. That is, when a patient's collected EMR stores information from a variety of different hospitals, pharmacies, urgent care clinics, doctors, specialists, etc., which information contained in these EMRs is particularly relevant to the patient's current medical care. It can be difficult to identify the problem and whether it is related to a particular treatment regimen previously prescribed to the patient. Therefore, there is a high possibility that there is also relevant information that may be overlooked. Furthermore, searching the EMR to find relevant information can be complex and confusing, leading to frustration on the part of medical professionals.

The illustrative embodiment provides a mechanism to emulate a medical professional's thinking about reviewing a patient's EMR to identify relevant information for treating the patient. Mechanisms are characteristics that indicate previously established patient treatment plans, follow-up to treatment plans, and specific patient information that will be investigated by health care professionals during current or upcoming interactions with patients. Identify the parts of the EMR that have . In some cases, this information may be identified based on the current reason for the patient interaction, such as, for example, the specific medical condition for which the patient is being seen or the specific medical condition for which the patient has scheduled an appointment. .

Before beginning a more detailed discussion of various aspects of the illustrative embodiments, the term "mechanism" throughout this description refers to elements of the invention that perform various operations, functions, and the like. It will be understood first that it will be used for A "mechanism," as that term is used herein, may be an implementation of a function or aspect of an exemplary embodiment in the form of an apparatus, procedure, or computer program product. In the case of a procedure, the procedure is performed by one or more devices, apparatus, computers, data processing systems, or the like. In the case of a computer program product, the logic represented by computer code or instructions embodied in or on the computer program product may be used to implement a function or to be associated with a particular "mechanism" Executed by one or more hardware devices to perform the operations. Accordingly, the mechanisms described herein may execute functions on specialized hardware, software running on general purpose hardware, software instructions stored on a medium such that the instructions may be readily executed by specialized or general purpose hardware. or a combination of any of the above.

The description and claims refer to specific features and elements of the exemplary embodiments using the terms "a," "at least one of," and "at least one of." "one or more of" may be used. These terms and phrases are intended to indicate that at least one of a particular feature or element is present in a particular illustrative embodiment, but that more than one may be present. That will be understood. That is, these terms/phrases are not intended to limit the description or claims to the presence of a single feature/element, but rather to require the presence of a plurality of such features/elements. It's not meant to be. On the contrary, these terms/phrases only require at least a single feature/element; a plurality of such features/elements may be within the scope of the description and claims.

Additionally, the use of the term "engine" as used herein with reference to described embodiments and features of the present invention refers to actions attributed to and/or performed by the engine; It will be understood that the invention is not intended to be limited to any particular implementation for accomplishing and/or performing the steps, processes, etc. The engine is software that is loaded or stored in machine-readable memory and that performs specified functions, including but not limited to the use of either a general purpose and/or special purpose processor in conjunction with appropriate software executed by the processor. , hardware, and/or firmware, or any combination thereof. Additionally, any names associated with particular engines, unless otherwise specified, are for convenience of reference and are not intended to limit the engine to any particular implementation. Additionally, any functionality attributed to an engine may be incorporated into and/or combined with the functionality of another engine of the same or different type, or in one or more of various configurations. It may equally be executed by multiple engines, distributed across multiple engines.

Additionally, the following description uses multiple various examples for various elements of the example embodiments to further illustrate example implementations of the example embodiments and to illustrate mechanisms of the example embodiments. It will be understood that promoting understanding. These examples are intended to be non-limiting and do not exhaust the various possibilities for implementing the mechanisms of the illustrative embodiments. It is understood that there are many other alternative implementations for these various elements that may be utilized in addition to or in place of the examples provided herein without departing from the spirit and scope of the invention. , will be apparent to those skilled in the art upon reviewing this description.

The invention may be a system, method, and/or computer program product. A computer program product may include computer readable storage medium(s) having computer readable program instructions for causing a processor to perform aspects of the present invention.

A computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. Not done. A non-exhaustive list of more specific examples of computer readable storage media include portable computer diskettes, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable memory, etc. Read-Only Memory (EPROM or Flash Memory), Static Random Access Memory (SRAM), Portable Compact Disk Read-Only Memory (CD-ROM), Digital Versatile Disk (DVD), Memory - Mechanically encoded devices such as sticks, floppy disks, punched cards or ridge-in-groove structures with instructions recorded thereon, and any suitable combinations of the foregoing. A computer-readable storage medium, as used herein, refers to radio waves or other freely propagating electromagnetic waves, such as electromagnetic waves propagating through waveguides or other transmission media (e.g., pulses of light passing through a fiber optic cable). , or electrical signals transmitted through wires, should not be construed as being inherently transient.

The computer-readable program instructions described herein may be transferred from a computer-readable storage medium to a respective computing/processing device or over, for example, the Internet, a local area network, a wide area network, or a wireless network; It can be downloaded to an external computer or external storage device via a network such as a combination thereof. The network may include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, or edge servers, or combinations thereof. A network adapter card or network interface within each computing device/processing device receives computer readable program instructions from the network for storage on a computer readable storage medium within the respective computing device/processing device. Transfer computer readable program instructions.

Computer-readable program instructions for carrying out operations of the present invention may include assembler instructions, instruction set architecture (ISA) instructions, machine language instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or Java ( one or more programming languages, including object-oriented programming languages such as R), Smalltalk(R), C++, or the like, and traditional procedural programming languages such as the "C" programming language, or similar programming languages; source code or object code written in any combination of The computer-readable program instructions can be executed as a stand-alone software package, entirely on a user's computer, partially on the user's computer, partially on the user's computer and partially remotely. - Can run on a computer or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or wide area network (WAN), or the connection may be (over the Internet using an Internet service provider) to an external computer. In some embodiments, electronic circuitry, including, for example, programmable logic circuitry, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is used to carry out aspects of the invention. In addition, the computer readable program instructions can be executed by personalizing the electronic circuitry using the state information of the computer readable program instructions.

Aspects of the invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart diagrams and/or block diagrams, as well as combinations of blocks in the flowchart diagrams and/or block diagrams, can be implemented by computer readable program instructions.

These computer readable program instructions are such that instructions executed by a processor of a computer or other programmable data processing device perform the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams. may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing device to produce the machine. These computer readable program instructions further include instructions for the computer readable storage medium on which the instructions are stored to perform aspects of the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams. It may be stored on a computer-readable storage medium and capable of instructing a computer, programmable data processing apparatus, and/or other device to function in a particular manner to provide the product.

The computer readable program instructions further include instructions for execution on a computer, other programmable apparatus, or other device to perform the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams. A device that is loaded into a computer, other programmable data processing equipment, or other device to cause the computer, other programmable equipment, or other device to perform a sequence of operational steps to produce a computer-implemented process. You can.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions that includes one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may actually be executed substantially concurrently, or the blocks may sometimes be executed in reverse order depending on the functionality involved. Each block in the block diagrams and/or flow diagrams, and combinations of blocks in the block diagrams and/or flowcharts, perform a designated function or act, or implement a combination of dedicated hardware and computer instructions. Note also that it can be performed by a dedicated hardware-based system.

The illustrative embodiments may be utilized in many different types of data processing environments. To provide context for the description of certain elements and features of the illustrative embodiments, FIGS. 1-3 are provided below as example environments in which aspects of the illustrative embodiments may be implemented. It will be appreciated that FIGS. 1-3 are merely examples and are not intended to depict or imply any limitations to the environments in which aspects or embodiments of the invention may be implemented. Many changes may be made to the depicted environment without departing from the spirit and scope of the invention.

1-3 illustrate a request processing pipeline, a request processing method, and a request processing computer program product (also referred to herein as a "healthcare cognitive system") in which the mechanisms of the illustrative embodiments are implemented. is intended to illustrate an example cognitive system for healthcare applications. These requests may be provided as structured or unstructured request messages or any other format suitable for requesting actions to be performed by a healthcare cognitive system. As explained in more detail below, specific healthcare applications realized with the cognitive system of the present invention include cognitive analysis and disambiguation of electronic medical records for the presentation of relevant information regarding medical care plans. is a healthcare application.

Although the healthcare cognitive system is shown in the examples below as having a single request processing pipeline, it will be appreciated that it may actually have multiple request processing pipelines. Each request processing pipeline may be separately trained and/or configured to handle requests associated with different disciplines, or may be configured as required for the desired implementation. Depending, the input requests may be configured to perform the same or different analysis. For example, in some cases, a first request processing pipeline may be trained to operate on input requests for a first medical disease field (e.g., various types of blood diseases); , another request processing pipeline may be trained to respond to input requests in another medical disease field (eg, various types of cancer). In other cases, for example, the request processing pipeline may be configured to provide various types of cognitive functionality or to support various types of healthcare applications, such as patient diagnosis. one request processing pipeline used for EMR data, another request processing pipeline configured for cognitive analysis of EMR data, another request processing pipeline configured for patient monitoring, etc. .

Additionally, each request processing pipeline accepts one corpus for documents in the blood diseases field and another for related documents in the cancer diagnostics field, e.g. in the above example, and applies can have its own associated corpus or corpora to work against. In some cases, request processing pipelines may each operate on the same field of input requests, but with different annotators, such that different analyzes and possible answers are generated, or , can have different configurations, each with a trained annotator. The healthcare cognitive system uses appropriate request processing pipes, including combining and evaluating the final results produced by the processing performed by multiple request processing pipelines, based on the determined field of the input request. Additional logic for routing input requests into lines and other control and interaction logic may be provided to facilitate the use of multiple request processing pipelines.

As will be discussed in more detail below, the illustrative embodiments are integrated into the functionality of a healthcare cognitive system's request processing pipeline and mechanism for electronic medical record integrity and data quality assessment mechanisms. , functionality can be expanded and expanded.

Therefore, before describing how the mechanisms of the illustrative embodiments integrate and extend such cognitive systems and request processing pipeline mechanisms, it is important to understand that when a cognitive system executes a request processing pipeline, It is important to first understand how the cognitive system operates. It is understood that the mechanisms described in FIGS. 1-3 are merely examples and are not intended to state or imply any limitations as to the types of cognitive system mechanisms under which the illustrative embodiments may be implemented. Good morning. Many modifications to the example cognitive systems illustrated in FIGS. 1-3 may be implemented in various embodiments of the invention without departing from the spirit and scope of the invention.

FIG. 1 depicts a schematic diagram of one illustrative embodiment of a cognitive system 100 that executes a request processing pipeline 108 in a computer network 102. Cognitive system 100 is connected to a computer network 102 (including one or more processors and one or more memory, as well as buses, storage devices, communication interfaces, and the like). may be implemented in one or more computing devices 104A-104C, potentially including any other computing device elements commonly known in the art. Merely by way of example, although FIG. 1 depicts cognitive system 100 implemented solely on computing device 104A, as noted above, cognitive system 100 may include multiple computing devices, such as multiple computing devices 104A-104C. may be distributed across the processing devices. Network 102 includes a plurality of computing devices 104A-104C that can operate as server computing devices and a plurality of computing devices 110-112 that can operate as client computing devices. and that communicate with each other and with other devices or components via one or more wired and/or wireless data communication links. Here, each communication link comprises one or more of a wire, router, switch, transmitter, receiver, or the like. In some illustrative embodiments, cognitive system 100 and network 102 can perform a number of functions depending on the desired implementation, such as, for example, cognitive information retrieval, user training/coaching, cognitive evaluation of data, or the like. Cognitive operations can be provided including, but not limited to, request processing and cognitive response generation, which can take different forms. Other embodiments of cognitive system 100 may be used with components, systems, subsystems, and/or devices other than those depicted herein.

Cognitive system 100 is configured to execute a request processing pipeline 108 that receives input from various sources. Requests may be submitted in the form of natural language requests, such as natural language requests for information, natural language requests for performing cognitive operations, etc. For example, cognitive system 100 receives input from network 102, one or more corpora of electronic documents 106, cognitive system users, or other data and other possible input sources, or combinations thereof. In one embodiment, some or all of the input to cognitive system 100 is routed through network 102. Various computing devices 104A-104C on network 102 include access points for content producers and cognitive system users. Some of the computing devices 104A-104C include devices for the database to store one or more corpora of data 106 (shown as separate entities in FIG. 1 for illustrative purposes only). . Portions of the one or more corpora of data 106 may also be stored on one or more other network-attached storage devices, in one or more databases, or otherwise not explicitly shown in FIG. may be provided to a computing device. Network 102 includes local network connections and remote connections in various embodiments such that cognitive system 100 can operate in any sized environment, including local and global, such as the Internet, for example.

In one embodiment, a content producer produces document content for one or more corpora of data 106 for use in cognitive system 100 as part of a corpus of data. A document includes any file, text, article, or data source for use with cognitive system 100. A cognitive system user accesses cognitive system 100 via a network connection to network 102 or an Internet connection and enters requests to cognitive system 100 that are processed based on the content of one or more corpora of data 106. do. In one embodiment, the request is formed using natural language. Cognitive system 100 parses and interprets the request via pipeline 108 and provides a response containing one or more responses to the request, results of processing the request, or the like, such as to a cognitive system user. 110 to a cognitive system user. In some embodiments, cognitive system 100 provides responses to the user in a ranked list of candidate responses, while in other illustrative embodiments, cognitive system 100 provides a single final response, or a combination of the final response and a ranked list of other candidate responses.

Cognitive system 100 executes a pipeline 108 that includes multiple stages for processing input requests based on information obtained from one or more corpora of data 106. Pipeline 108 processes the input request and generates a response to the input request based on one or more corpora of data 106.

As mentioned above, input from a client device to cognitive system 100 may be submitted in the form of natural language requests, although the illustrative embodiments are not limited to such. Rather, the input request actually involves the natural language parsing and analysis mechanisms of cognitive systems such as IBM Watson (TM) to determine the basis for performing the cognitive analysis and providing the results of the cognitive analysis. The request may be formatted or structured as any suitable type of request that may be parsed and analyzed using, but not limited to, structured and/or unstructured input analysis. For healthcare-based cognitive systems, this analysis involves processing patient medical records, medical instructional documents from one or more corpora, and the like to provide healthcare-oriented cognitive system results. It can include doing.

In the context of the present invention, cognitive system 100 may provide cognitive functionality to assist in healthcare-based operations. For example, depending on the particular implementation, healthcare-based operations may include patient diagnostics, medical practice management systems, personal patient care plan generation and monitoring. ion and monitoring) , or may include patient electronic medical record (EMR) evaluation for various purposes. Accordingly, the cognitive system 100 operates in a medical or healthcare type field and processes such requests via the request processing pipeline 108, which may be input as structured or unstructured requests, natural language input, or the like. The healthcare cognitive system 100 may be capable of processing requests for healthcare operations.

As shown in FIG. 1, cognitive system 100 provides cognitive analysis and disambiguation that emulates the thinking of a medical professional about reviewing a patient's EMR to identify relevant information for treating the patient. to include logic running on dedicated hardware, software running on hardware, or any combination of dedicated hardware and software running on hardware to execute engine 120; It is further expanded upon according to the mechanism of the illustrative embodiment. Cognitive analysis and disambiguation engine 120 uses knowledge obtained from a variety of different sources of medical information to determine which information is most important when investigating a medical condition. Cognitive analysis and disambiguation engine 120 uses a medical mental model that emulates a medical professional's thinking about reviewing a patient's EMR to identify relevant information regarding the medical care plan.

Cognitive analysis and disambiguation engine 120 uses natural language processing (NLP) and heuristics to identify instances of such information within a patient's EMR data. The cognitive analysis and disambiguation engine 120 analyzes what was done before treating the patient, what treatment was planned for the patient, how the medical condition was originally diagnosed, the patient's goals and Medical mental models are used to look for instances of information in the patient's EMR data that address what the social determinants were, what motivates the patient to adhere to the treatment plan, etc. Cognitive analysis and disambiguation engine 120 extracts meaning from these using medical mental models, and processes the specific medical condition or reason for the patient's current or upcoming interaction with a medical professional. Particular focus is placed on

As discussed above, the mechanisms of the illustrative embodiments are rooted in the computer technology field and are implemented using logic residing within such computing or data processing systems. These computing or data processing systems are specifically configured by hardware, software, or a combination of hardware and software to perform the various operations described above. Accordingly, FIG. 2 is shown as an example of one type of data processing system in which aspects of the invention may be implemented. Many other types of data processing systems may be similarly configured to specifically implement the mechanisms of the illustrative embodiments.

FIG. 2 is a block diagram of an example data processing system in which aspects of the example embodiments are implemented. Data processing system 200 is an example of a computer, such as server 104 or client 110 of FIG. 1, in which there is computer-usable code or instructions that perform processing for an illustrative embodiment of the invention. In one illustrative embodiment, FIG. 2 represents a server computing device, such as server 104, that includes additional mechanisms of the illustrative embodiment described below. A cognitive system 100 and a QA system pipeline 108 are executed.

In the depicted example, data processing system 200 includes a north bridge and memory controller hub (NB/MCH) 202 and a south bridge and input/output (I/O) controller hub (SB/ICH) 204. Adopt a hub architecture that includes Processing unit 206, main memory 208, and graphics processor 210 are connected to NB/MCH 202. Graphics processor 210 is connected to NB/MCH 202 via an accelerated graphics port (AGP).

In the depicted example, a local area network (LAN) adapter 212 connects to SB/ICH 204 . audio adapter 216, keyboard and mouse adapter 220, modem 222, read-only memory (ROM) 224, hard disk drive (HDD) 226, CD-ROM drive 230, universal serial bus (USB) port, and others. communication port 232 and PCI/PCIe devices 234 connect to SB/ICH 204 via bus 238 and bus 240. PCI/PCIe devices can include, for example, Ethernet adapters, add-in cards, and PC cards for notebook computers. PCI uses a card bus controller, while PCIe does not. ROM 224 may be, for example, a flash basic input/output system (BIOS).

HDD 226 and CD-ROM drive 230 connect to SB/ICH 204 via bus 240. HDD 226 and CD-ROM drive 230 may use, for example, integrated drive electronics (IDE) or serial advanced technology attachment (SATA) interfaces. Super I/O (SIO) device 236 is connected to SB/ICH 204.

An operating system runs on processing unit 206. The operating system coordinates and provides control of various components within data processing system 200 of FIG. 2. The operating system as a client is a commercially available operating system such as Microsoft(R) Windows(R) 10(R). An object-oriented programming system, such as a Java(R)(TM) programming system, can operate in conjunction with an operating system, and can be used to program the operating system from a Java(R)(TM) program or application running on data processing system 200. Make a call to.

The data processing system 200 as a server is, for example, an IBM(R) eServer(TM) System p(R) computer running an Advanced Interactive Executive (AIX(R)) operating system or a LINUX(R) operating system. It may be a system. Data processing system 200 may be a symmetric multiprocessor (SMP) system with multiple processors within processing unit 206. Alternatively, a single processor system may be employed.

Instructions for the operating system, object-oriented programming system, and applications or programs reside on a storage device, such as HDD 226, and are loaded into main memory 208 for execution by processing unit 206. Processing for exemplary embodiments of the invention resides in computer-usable program code residing, e.g., in memory, such as main memory 208, ROM 224, or, e.g., in one or more peripheral devices 226 and 230. is performed by processing unit 206 using .

A bus system, such as bus 238 or bus 240 as shown in FIG. 2, is comprised of one or more buses. Of course, a bus system may be implemented using any type of communication fabric or architecture that provides data transfer between various components or devices attached to the communication fabric or architecture. A communication unit, such as modem 222 or network adapter 212 in FIG. 2, includes one or more devices used to send and receive data. The memory may be, for example, main memory 208, ROM 224, or a cache such as that found in NB/MCH 202 of FIG.

Those skilled in the art will appreciate that the hardware depicted in FIGS. 1 and 2 may vary depending on the implementation. Other internal hardware or peripheral devices, such as flash memory, equivalent non-volatile memory, or optical disk drives, and the like, may be in addition to or in addition to the hardware depicted in FIGS. 1 and 2. Alternatively, it may be used. Additionally, the processing of the illustrative embodiments may be applied to multiprocessor data processing systems other than the previously mentioned SMP systems without departing from the spirit and scope of the invention.

Additionally, data processing system 200 may include a client computing device, a server computing device, a tablet computer, a laptop computer, a telephone or other communication device, a personal digital assistant (PDA), or the like. It may take the form of any of several different data processing systems, including: In some illustrative examples, data processing system 200 is configured with flash memory, for example, to provide non-volatile memory for storing operating system files and/or user-generated data. It may also be a portable computing device. Essentially, data processing system 200 may be any known or later developed data processing system without limitation in construction.

FIG. 3 is an illustration of an example diagram illustrating the interaction of elements of a healthcare cognitive system according to one illustrative embodiment. The example diagram of FIG. 3 depicts an implementation of a healthcare cognitive system 300 configured to provide a cognitive overview of a patient's EMR data. However, it is understood that this is only an example implementation and that other medical operations may be implemented in other embodiments of healthcare cognitive system 300 without departing from the spirit and scope of the invention. Good morning.

Further, although FIG. 3 depicts user 306 as a human figure, interactions with user 306 may occur using a computing device, medical equipment, or the like, or a combination thereof. As a result, it will be appreciated that user 306 may actually be a computing device, such as, for example, a client computing device. For example, interactions between the user 306 and the healthcare cognitive system 300 may be conducted via one or more data communication links and potentially one or more data networks with the healthcare cognitive system 300. The communication may be electronic through a user computing device (not shown), such as client computing device 110 or 112 of FIG.

As shown in FIG. 3, according to one illustrative embodiment, a user 306 sends a request to the healthcare cognitive system 300 in a format that the healthcare cognitive system 300 can parse and process. sends a request 308 to the healthcare cognitive system 300, such as via a user interface on a client computing device configured to allow the sender to send the request. Request 308 may include or be appended with information identifying patient attributes 318. These patient attributes 318 may include, for example, the patient's 302 identifier, demographic information about the patient, symptoms, and other relevant information obtained from the response to the request, or the patient's patient EMR 322 may be searched for. may include information obtained from medical devices used to monitor or collect data about the condition of the patient. Any information about the patient that may be relevant to the patient's cognitive assessment by the healthcare cognitive system 300 may be included in the request 308 and/or patient attributes 318.

Healthcare cognitive system 300 provides a cognitive system specifically configured to perform implementation-specific healthcare-oriented cognitive operations. In the depicted example, this healthcare-oriented cognitive operation is performed by the EMR to assist the user 306 in treating the patient based on the patient's reported symptoms and other information gathered about the patient. It is for providing a cognitive overview 328 of the data to the user 306. Healthcare cognitive system 300 operates on requests 308 and patient attributes 318 and includes information gathered from medical corpora and other sources of data 326, treatment guidance data 324, and patient EMRs 322 associated with the patient. A cognitive summary 328 is generated using the cognitive summary 328. A cognitive summary 328 is obtained from patient attributes 318 and data sources 322-326 and ranked with associated corroborating evidence that provides an inference as to why the portion of EMR data 322 is being provided. May be presented in order.

According to illustrative embodiments herein, healthcare cognitive system 300 emulates a medical professional's thinking about reviewing a patient's EMR 322 to identify relevant information for treating the patient. The cognitive analysis and disambiguation engine 320 is expanded to include a cognitive analysis and disambiguation engine 320. Cognitive analysis and disambiguation engine 320 uses medical mental models generated based on knowledge extracted from various sources, such as treatment guidance data 324 and data 326 from medical corpora and other sources. Cognitive analysis and disambiguation engine 320 uses natural language processing (NLP) and heuristics to identify instances of information within EMR 322. Cognitive analysis and disambiguation engine 320 uses medical mental models to identify passages in patient EMR 322 and extract meaning from the passages. Cognitive analysis and disambiguation engine 320 uses this information to generate a cognitive summary of the patient's medical record that is consistent with the medical mental model and answers typical questions about the patient's health status. These are the status of the health condition, the plan of action for this condition, what happened as a result of the intervention and what elements should be followed up by the health care professional during the current or upcoming interaction with the patient. Including questions about.

FIG. 4 depicts an example medical mental model according to an illustrative embodiment. A medical mental model is represented as a graph data structure with connected nodes. The medical mental model includes a root node 400 connected to a patient information node 401, a time view node 402, and a next-to-do node 403. Patient information node 401 represents patient information that a medical professional would look for within a patient EMR. The patient information node 401 connects to multiple child nodes such as intervention goals, indicative measurements, medications 411, plans for each visit, what happened, patient life goals, and social determinants nodes. be done. These nodes may include words or phrases that indicate data regarding the medical plan.

In the depicted example, drug treatment node 411 is connected to child nodes such as start, stop 421, and increase dose nodes. The abort node 421 is connected to a reason node 431 which is a child node. In the depicted example, discontinuation node 421 represents a word, phrase, or other data to find within the patient EMR when the patient discontinues receiving a given drug treatment. Reason node 431 may represent a word, phrase, or other data for finding within the patient EMR the reason why the patient stopped receiving a given drug treatment.

The medical mental model can further include prototype questions that a medical professional might ask the healthcare cognitive system about the patient EMR. For example, reason model 431 may include the question, "Why did the patient stop taking medication?" Using the medical mental model, the cognitive analysis and disambiguation engine can inject prototype questions from the medical mental model into the healthcare cognitive system, and the healthcare cognitive system can inject prototype questions about parts of the patient EMR. will return the answer.

Mental models may be specific to a particular medical professional and a particular medical condition. Thus, there may be multiple medical mental models for a particular medical professional, one for each medical condition for which a patient can be treated by the medical professional. For example, there may be separate medical mental models for hypertension and diabetes. Additionally, each medical mental model may be specific to how this medical professional reviews patient EMR data for a given medical condition.

FIG. 5 is a block diagram illustrating a mental model instantiation engine according to an illustrative embodiment. Mental model instantiation engine 500 includes an interaction monitoring component 501, a natural language processing (NLP) component 502, a machine learning component 503, and a medical mental model instantiation component 504. Mental model instantiation engine 500 receives a medical mental model 521 that is generated using knowledge obtained from a variety of different sources of medical information during an examination by a medical professional. Medical mental model 521 emulates a medical professional's thinking about reviewing a patient's electronic medical record (EMR) and specifies what information is most important when investigating a medical condition.

In one embodiment, medical mental model 521 may be a comprehensive model for all medical professionals in all disciplines. Alternatively, mental model instantiation engine 500 receives one or more medical mental models 521 corresponding to each medical condition. For example, one medical mental model may be for oncologists, while another medical mental model may be for cardiologists, and yet another medical mental model may be for cardiologists. The mental model may be for a pediatrician.

Each hospital, each medical office, or even each individual medical professional may have a separate mental model. For example, when treating a patient with heart disease, one health care professional may look at test results first, while another health care professional may give higher priority to dietary and lifestyle information. can be placed. Thus, according to an illustrative embodiment, mental model instantiation engine 500 receives a more general medical mental model 521 and creates a more specific medical model for a given hospital, medical office, or individual medical professional. An instance 525 of the medical mental model is generated.

Interaction monitoring component 501 monitors user interaction with electronic medical record 522 using input device 511 and display 512. Input device 511 may include a keyboard, mouse, or other known or future input device. As a user interacts with EMR data 522, interaction monitoring component 501 determines which questions the user asked, which parts of the EMR the user viewed, the order in which the user asked the questions, and which parts of the EMR the user viewed. information such as the order, whether the user hovered a mouse cursor at a particular location within the EMR, whether the user zoomed in on a portion of an image within the EMR, etc.

Natural language processing (NLP) component 502 performs natural language processing on the portion of EMR data 522 that is being viewed by the medical professional. NLP component 502 can analyze a portion of EMR data 522 to determine keywords or phrases that may be relevant to a medical plan for a particular medical condition. This information extracted from the portion of the EMR that the medical professional is viewing then identifies differences between the medical professional's interaction with the EMR data 522 and the prevailing medical mental model 521. may be used for

Machine learning component 503 uses machine learning techniques to learn differences between a medical professional's interaction with EMR data 522 and a general medical mental model 521. That is, machine learning component 503 learns when and how a medical professional deviates from medical mental model 521 when interacting with patient EMR data 522.

The medical mental model instantiation component 504 generates a medical mental model instance 525 based on the learned differences between the interaction with the patient EMR 522 and the medical mental model 521. The medical mental model instance 525 emulates a particular medical office or individual medical professional's thoughts about reviewing a patient's EMR to identify relevant information regarding the medical care plan. The medical mental model instance 525 is based on usage trends learned from the medical professional's interaction with the patient EMR, words or phrases indicating the patient treatment plan, patient information to be viewed, and patient information. and the prototype questions that would be asked about patient treatment based on the patient EMR. A medical mental model instance 525 is a data structure that organizes a medical professional's thinking when reviewing a patient EMR for a particular medical condition. In one embodiment, the medical mental model instance 525 may be in the form of a graph data structure. Alternatively, the medical mental model instance 525 may be an extensible markup language (XML) document. Other types of data structures, such as linked tables or the like, may be used within the spirit and scope of the illustrative embodiments.

FIG. 6 is a block diagram illustrating a cognitive analysis and disambiguation engine according to an illustrative embodiment. The cognitive analysis and disambiguation engine 600 includes a natural language processing component 601, a heuristic component 602, an EMR data selection component 603, a meaning extraction component 604, a prototype question answering component 605, and a cognitive overview component. Includes a generation component 606. The cognitive analysis and disambiguation engine 600 organizes and outlines the state-specific data and context according to the medical mental model instance 625 (correlated relationship information) for the patient visit.

Natural language processing (NLP) component 601 and heuristics component 602 use NLP and heuristics to identify instances of information within EMR 620 that are most important when investigating a medical condition. Using the medical mental model instance 625, the natural language processing component 601 and the heuristics component 602 determine what was done before treating the patient and what was the treatment planned for the patient. , how the condition was originally diagnosed, what the patient's goals and social determinants of goals were, what motivates the patient to adhere to the treatment plan, etc. Find instances of information. EMR data selection component 603 then selects the identified portion of patient EMR 620 using NLP component 601 and heuristic component 602.

The meaning extraction component 604 identifies a passage in the patient EMR 620 using an instance 625 of a medical mental model, extracts meaning from the passage, and processes a particular medical condition or a patient's current or upcoming Particular focus will be placed on the reasons for dialogue with medical professionals. For example, the EMR data selection component 603 may select a portion of the patient EMR data 620 that is related to drug therapy performed by the patient to treat a medical condition, and the meaning extraction component 604 may select from this portion: It is possible to extract that the patient has stopped administering the first drug treatment and that the patient has started administering the second drug treatment.

Accordingly, the information in the medical mental model instance 625 may then be relevant to the treatment of the medical condition, such as, for example, for a particular sentence in the patient EMR 620, whether the features of the sentence match elements of a treatment plan for the medical condition. A patient's EMR is used to identify portions of a patient's EMR for a particular medical condition. Once identified, the meaning extraction component 604 extracts meaning from the identified portion by analyzing the portion using an instance of the medical mental model 625 to create a treatment plan for the medical condition. Extract relevant patient information.

In applying the medical mental model instance 625, the prototype question answering component 605 utilizes prototype questions about treatment of the medical condition to extract answers from the identified portions of the patient EMR 620.

The cognitive summary generation component 606 generates a cognitive summary of the patient's EMR 620 that is consistent with the medical mental model instance 625 and answers typical questions about the patient's health status. These are the status of the health condition, the plan of action for this condition, what happened as a result of the intervention and what elements should be followed up by the health care professional during the current or upcoming interaction with the patient. Including questions about. The cognitive summary may then be displayed to the medical professional on display 612.

FIG. 7 is a flow diagram of a mechanism for instantiating a medical mental model according to an illustrative embodiment. Operation begins (block 700) and the mechanism selects a medical professional's specialty or general medical mental model for the medical condition being treated (block 701). A mechanism monitors a medical professional's interaction with an electronic medical record (EMR) (block 702). The mechanism identifies words or phrases that indicate medical plans, follow-up, disease indicators, etc. (block 703). Next, the mechanism identifies differences between the medical professional's interaction with the patient EMR data and the prevailing medical mental model (block 704). The mechanism generates an instance of a medical mental model that emulates a particular medical office or individual medical professional's thoughts about reviewing the patient's EMR to identify relevant information regarding the medical care plan (block 705). . The operation then ends (block 706).

FIG. 8 is a flow diagram illustrating the operation of a mechanism for cognitive analysis and disambiguation of electronic medical records for presentation of relevant information regarding a medical plan, according to an illustrative embodiment. Operation begins (block 800), and the mechanism performs natural language processing and heuristic analysis on the patient EMR to identify instances of information that are relevant to the patient's treatment plan (block 801). The mechanism analyzes the identified portion of the EMR to extract relevant patient information for treatment planning (block 802). The mechanism then applies the prototype questions from the medical mental model to the identified portion of the EMR (block 803). The mechanism generates a cognitive summary of the EMR based on the medical mental model (block 804). The operation then ends (block 805).

As noted above, an exemplary embodiment may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment containing both hardware and software elements. That will be understood. In one example embodiment, the mechanisms of the example embodiment are implemented in software or program code, including but not limited to firmware, resident software, microcode, and the like.

A data processing system suitable for storing and/or executing program code includes at least one processor coupled directly or indirectly to storage elements through a communication bus, such as a system bus. It turns out. Storage elements are used to store local memory, mass storage used during the actual execution of program code, and at least some programs to reduce the number of times the code must be retrieved from mass storage during execution. - Can include cache memory to provide temporary storage of code. The memory may be of various types including, but not limited to, ROM, PROM, EPROM, EEPROM, DRAM, SRAM, flash memory, solid state memory, and the like.

Input/output or I/O devices (including, but not limited to, keyboards, displays, pointing devices, etc.) may be used directly or through intervening wired or wireless I/O interfaces and/or controllers. Or something similar can be coupled to the system. I/O devices include, for example, communication devices coupled via wired or wireless connections, including, but not limited to, smart phones, tablet computers, touch screen devices, voice recognition devices, and the like. The device may take many different forms other than traditional keyboards, displays, pointing devices, and the like. Any known or later developed I/O device is intended to be within the scope of the illustrative embodiments.

Network adapters are also installed on the system to enable the data processing system to become coupled to other data processing systems or to remote printers or storage devices through intervening private or public networks. may be connected to Modems, cable modems, and Ethernet cards are just a few of the types of network adapters for wired communications currently available. Wireless communication-based network adapters may further be utilized, including but not limited to 802.11a/b/g/n wireless communication adapters, Bluetooth wireless adapters, and the like. Any known or later developed network adapter is intended to be within the spirit and scope of the present invention.

The description of the invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or restrictive to the invention in the form disclosed. Many modifications and variations will be apparent to those skilled in the art without departing from the scope of the described embodiments. The embodiments are presented in a manner that best explains the principles and practical application of the invention, and which will enable those skilled in the art to understand the invention in its various embodiments with various modifications as appropriate for the particular use contemplated. were selected and written in a way that is easy to understand. The terminology used herein is used in a manner that best describes the principle, practical application, or technical improvement of the embodiments to those found in the marketplace, or that otherwise describes the embodiments disclosed herein. It was chosen so that it would be understandable to contractors.

Claims (13)

A method by which a processor performs
receiving the medical condition for interaction with the patient's current or upcoming health care professional by a cognitive analytics engine;
receiving, by the cognitive analytics engine, an instance of a medical mental model that emulates a medical professional's thoughts about reviewing a patient electronic medical record (EMR) to identify relevant information regarding a medical care plan for the medical condition; And,
analyzing the EMR of the patient by the cognitive analysis engine using the instance of the medical mental model to identify at least one portion of the EMR related to the medical care plan;
analyzing at least one portion of the identified EMR by the cognitive analysis engine using the instance of the medical mental model to extract relevant patient information for the medical care plan regarding the medical condition; ,
Using an instance of the medical mental model, the cognitive analysis engine generates information about the patient's health consistent with the medical mental model that correlates with the extracted relevant patient information and the medical plan regarding the medical condition. generating and outputting a cognitive summary of the EMR that answers typical questions about a condition. 2. The method of claim 1, wherein analyzing the EMR of the patient includes identifying follow-up to the medical plan in the EMR. 3. The method of claim 1 or 2, wherein analyzing the EMR of the patient includes identifying patient condition indicators associated with the medical care plan in the EMR. 4. A method according to any one of claims 1 to 3, wherein the instance of the medical mental model is specific to the medical condition. Claim 1, wherein the instance of the medical mental model is specific to the medical professional.
The method according to any one of 3 to 3. At least one portion of the identified EMR related to the medical care plan includes at least one of a plan for treatment of the patient, follow-up of the patient, a subjective evaluation of the patient, and objective values. , a method according to any one of claims 1 to 5. Claims 1-6, wherein analyzing the identified at least one portion of the EMR comprises applying a prototype question from an instance of the medical mental model to the identified at least one portion of the EMR. The method described in any one of the above. selecting a general medical mental model;
monitoring a medical professional's interaction with said EMR;
identifying differences between the medical professional's interaction with the EMR and the general medical mental model;
8. The method of any preceding claim, further comprising: generating an instance of the medical mental model based on the identified differences. Identifying the differences uses machine learning techniques to learn when and how the medical professional deviates from the prevailing medical mental model when interacting with the EMR. 9. The method of claim 8, comprising: 10. The method of any one of claims 1 to 9, wherein the medical mental model instance comprises at least one of a graph data structure or an extensible markup language document. A computer program product causing a processor to perform the method according to any one of claims 1 to 10. A computer-readable storage medium having recorded thereon a computer program for causing a processor to perform the method according to any one of claims 1 to 10. A device,
a processor;
a memory coupled to said processor, said memory comprising a computer program for causing said processor to perform a method according to any one of claims 1 to 10.

Images